© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 124053
    Prev
    Next
    INDEX
    Explanations

    future going to be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    即便是
    -1.48
     بعدی
    -1.46
    layer
    -1.46
    olving
    -1.44
    七八
    -1.43
     playera
    -1.41
     paisajes
    -1.40
    rfan
    -1.40
    beit
    -1.38
    WHAT
    -1.38
    POSITIVE LOGITS
     a
    1.71
     Looks
    1.45
     some
    1.41
     an
    1.38
     tenemos
    1.27
    quartz
    1.27
    ječ
    1.24
     as
    1.23
     be
    1.21
     was
    1.21
    Activations Density 0.015%

    No Known Activations